RETRACTED: Deep Logistic Learning Framework for E-Commerce and Supply Chain Management Platform (Retracted Article)

Recently, the rapid development of e-commerce faces various challenges in information maintenance during online transactions and purchases. Presently, server error and security threats are an interactive method of payment; inconsistent data dissemination issues and prolonged customer waiting time during online purchase and transaction lead to several concerns based on supply chain management during the delivery of products. An essential component of e-commerce is the online transaction portal to ensure specific transactions with conflicts free and ensuring cyber security. Hence, this research develops a deep logistic learning framework (DLLF) to minimize computational time and improve data dissemination accuracy during an online transaction. Furthermore, the DLLF model has been designed based on deep logistic and sampled structure using a controlled network approach and integrated learning system to minimize the computational time and improve accuracy in maintaining customer data. Simulation analysis shows that user behaviors proposed framework analysis improves precision and minimizes computation time during the online purchase effectively with cyber security. The experimental results show DLLF has high efficiency (95.1%), enhanced customer satisfaction (92.6%), less error rate (21.4%), performance rate (94.3%), improved data prediction (91.2%), cost-effectiveness (94.5%), overall production (93.6%) when compared to other methods.